Run workers on a task

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a destructive, non-read-only mutation, and the description earns extra credit by disclosing the side effects: the task is marked in progress, credits are consumed, and the call fails when the workspace is out of credits. It also documents the reuse behavior ('if a run is already open, returns that run instead of starting another') and points to heliyos_runs_get for follow-up, which is exactly the behavioral context annotations alone cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each doing distinct work: action, repeat-call behavior, cost/failure mode, then return shape and next step. The action and the run_id handoff are front-loaded with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation that spends credits, the description covers the action, the side effect, the failure condition, the tax on repeat calls, and the return contract, which is more than an output schema alone conveys. Nothing an agent needs before calling or immediately after is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single required task_id and 100% schema description coverage including a 24-character hex pattern, the schema already covers the only parameter. The description adds no format, constraint or validation guidance beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Starts the workers (AI agents) on one task now and marks it in progress.' It also distinguishes this tool from the adjacent read tool by naming heliyos_runs_get as the follow-up for the resulting run_id, so an agent can tell it apart from heliyos_tasks_get, heliyos_tasks_update and heliyos_runs_* without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The word 'now' implies this is the immediate-execution path, and the return of an existing open run gives some context on repeat calls. However, the description never states when an agent should call this instead of heliyos_tasks_update or a future-scheduled path, and it gives no prerequisites such as required credits or task state.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.